Logo do repositório
 
Publicação

Protocol for evaluating ChatGPT in biomedical association generation and verification using a RAG enabled, cross-model majority voting workflow

2026-06-19Artigo de investigação Acesso aberto
Ver registo simples
dc.contributor.authorHamed, Ahmed Abdeen
dc.contributor.authorRocha, Luis M.
dc.date.accessioned2026-06-01T17:11:00Z
dc.date.available2026-06-01T17:11:00Z
dc.date.issued2026-06-19
dc.description.abstractWe present a protocol to evaluate ChatGPT’s ability to generate disease-centric biomedical associations. It outlines how we generate the associations, validate the biological entities using biomedical ontologies, and verify associations using literature. The protocol includes a self-consistency strategy to assess generative reliability across ChatGPT models. To address ontology exact-match limitations, we provide a use case performing semantic verification through a workflow enabled by Retrieval-Augmented Generation (RAG) powered by open-source large language models (LLMs). This enables LLMs to establish truth over content generated by other LLMs and expose hallucination.eng
dc.identifier.doi10.1016/j.xpro.2026.104533
dc.identifier.other86b79572-383d-4002-9814-6a03816ee030
dc.identifier.pmid42133493
dc.identifier.urihttp://hdl.handle.net/10400.14/57885
dc.identifier.wos001770377700001
dc.language.isoeng
dc.peerreviewedyes
dc.publisherCell Press
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/4.0/
dc.titleProtocol for evaluating ChatGPT in biomedical association generation and verification using a RAG enabled, cross-model majority voting workflow
dc.typeresearch article
dspace.entity.typePublication
oaire.citation.issue2
oaire.citation.volume7
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
150860178.pdf
Tamanho:
5.8 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

CBR - Contribuições em Revistas Científicas / Contribution to Journals